This study deploys methods in explainable artificial intelligence (XAI), e.g. decision trees and Pearson's correlation coefficient (PCC), to investigate electricity usage in multiple locales. It addresses the vital issue of energy burden, i.e. total amount spent on energy divided by median household income. Socio-demographic data is analyzed with energy features, especially using decision trees and PCC, providing explainable predictors on factors affecting energy burden. Based on the results of the analysis, a pilot energy equity web portal is designed along with a novel energy burden calculator. Leveraging XAI, this portal (with its calculator) serves as a prototype information system that can offer tailored actionable advice to multiple energy stakeholders. The ultimate goal of this study is to promote greater energy equity through the adaptation of XAI methods for energy-related analysis with suitable recommendations.

We use large language models to aid learners enhance proficiency in a foreign language. This is accomplished by identifying content on topics that the user is interested in, and that closely align with the learner's proficiency level in that foreign language. Our work centers on French content, but our approach is readily transferable to other languages. Our solution offers several distinctive characteristics that differentiate it from existing language-learning solutions, such as, a) the discovery of content across topics that the learner cares about, thus increasing motivation, b) a more precise estimation of the linguistic difficulty of the content than traditional readability measures, and c) the availability of both textual and video-based content. The linguistic complexity of video content is derived from the video captions. It is our aspiration that such technology will enable learners to remain engaged in the language-learning process by continuously adapting the topics and the difficulty of the content to align with the learners' evolving interests and learning objectives. A video showcasing our solution can be found at: https://youtu.be/O6krGN-LTGI

The consumption of microbial-contaminated food and water is responsible for the deaths of millions of people annually. Smartphone-based microscopy systems are portable, low-cost, and more accessible alternatives for the detection of Giardia and Cryptosporidium than traditional brightfield microscopes. However, the images from smartphone microscopes are noisier and require manual cyst identification by trained technicians, usually unavailable in resource-limited settings. Automatic detection of (oo)cysts using deep-learning-based object detection could offer a solution for this limitation. We evaluate the performance of three state-of-the-art object detectors to detect (oo)cysts of Giardia and Cryptosporidium on a custom dataset that includes both smartphone and brightfield microscopic images from vegetable samples. Faster RCNN, RetinaNet, and you only look once (YOLOv8s) deep-learning models were employed to explore their efficacy and limitations. Our results show that while the deep-learning models perform better with the brightfield microscopy image dataset than the smartphone microscopy image dataset, the smartphone microscopy predictions are still comparable to the prediction performance of non-experts.

In some cases, these AI advisors have become a standard part of some firms' project delivery methods. But it's still a challenge to convince construction professionals to listen to these AI advisors, and there are emerging questions of how risk will be allocated once algorithm-driven decisions start to steer projects. One of the more direct uses of AI in construction has been the project scheduling analysis performed by ALICE Technologies' machine-learning algorithm, ALICE. The company has made inroads into the industry in recent years (ENR 5/28/18 p.22), but founder René Morkos says that construction may be approaching a tipping point when it comes to AI adoption. "What I always hear from people [in the industry] is that'I really like scheduling, but the number crunching is the boring part,'" says Morkos.

Early adopting providers such as Sharp Healthcare and UPMC have been keen on seeing how far they can push the complex but extraordinarily helpful technology today, knowing that AI will play a much bigger role in their organizations tomorrow. "Currently, very little artificial intelligence is being utilized across the healthcare sector overall," said Brett MacLaren, vice president of enterprise analytics at Sharp HealthCare. "At Sharp, we are using predictive algorithms to predict a patient's propensity to pay their bill, and are leveraging that insight to prioritize who to contact and negotiate with to increase their likelihood of payment." In addition, Sharp HealthCare recently completed a proof of concept to develop an algorithm to predict patient decline in the acute care setting by analyzing its electronic health record data to see when rapid response teams are called in to intervene on its sickest patients. "At this point, we have not quantified the additional value the predictive algorithm on a patient's propensity to pay has bill provided to our bottom line, but the consensus is that it has been worthwhile," MacLaren said.

There is a lot of hype around using artificial intelligence (AI) technologies in care provider settings. Last week, the University of Pittsburgh Medical Center's (UPMC) partnered with Microsoft, an expert in AI tools, to launch the first project under the new Healthcare NExt initiative aimed at improving clinicians' workflow, signaling continued interest and investment in the healthcare AI space. The nonprofit, which operates 25 hospitals and 600 doctors' offices and outpatient facilities, is at the forefront of the healthcare AI wave. It invests in the companies that create AI capabilities and launches its own startups, in addition to implementing co-created technologies for its clinicians to use with their patients. Dr. Rasu Shrestha, UPMC chief innovation officer and executive vice president of UPMC Enterprises, the institution's commercialization arm, told Healthcare Dive that its AI technologies has resulted in "quite the transformation" as they have allowed for an increased ...

Rasu Shrestha, M.D., the chief innovation officer at the Pittsburgh-based UPMC health system, serves as the chair of the Informatics Scientific Program Committee at the Radiological Society of North America. In that role, Dr. Shrestha has led the discussions that have created the official theme each year for the past two years, for the imaging informatics content at the annual RSNA Conference. Last year, the theme was 3D printing; this year, it is machine learning. Dr. Shrestha took out time on Nov. 29 during the frenzy of activity at RSNA 2016, being held at the McCormick Place Convention Center in Chicago, to speak with Healthcare Informatics Editor-in-Chief Mark Hagland, about the current state and future prospects of radiology practice and of imaging informatics. Below are excerpts from that interview.

When Uber chose to test its robot-driven taxis in Pittsburgh, some may have wondered why the tech company had chosen America's former capital of steel for its road test into the future. But for those in the know, Pennsylvania's second city is well on its way to establishing itself as the Silicon Valley of the east – and even its roads are helping. Unlike many American cities, Pittsburgh road system is literally off the grid, its origins dating back to twisty, pre-revolution forest trails. Then there are the city's 446 bridges to navigate. More importantly Pittsburgh boasts the robotics department at Carnegie-Mellon University, recognized as the leading academic institution in the field. It was here last month that Pittsburgh opened its doors to show the world why it is so well positioned to be a new tech hub.

The experimental Smart Tissue Autonomous Robot (STAR) recently sewed a piglet's gut together using a computer program and camera-based guidance, overseen by a team of doctors and computer scientists from the Children's National Health System in Washington DC and Johns Hopkins University. The procedure took 50 minutes, as opposed to 8 minutes when performed by a surgeon, but (unfortunately for doctors) resulted in more evenly spaced sutures and less leakage from the gut. And with iterative improvements, it's likely that the time difference can be shrunk. Meanwhile, FDA-approved robotic surgery on humans is making strides as well, though it requires a surgeon to operate the mechanical arm. The potential treatment paradigm, highlighted by The Economist this month, raises questions about whether patients will trust robots with their lives, and who is liable if something goes wrong. Another question robots pose: Are doctors in line for a string of layoffs?